相关论文: Style Pooling: Automatic Text Style Obfuscation fo…

This paper presents an algorithm for enumerating biases in word embeddings. The algorithm exposes a large number of offensive associations related to sensitive features such as race and gender on publicly available embeddings, including a…

In this paper, we investigate the efficacy of large language models (LLMs) in obfuscating authorship by paraphrasing and altering writing styles. Rather than adopting a holistic approach that evaluates performance across the entire dataset,…

Users' interaction or preference data used in recommender systems carry the risk of unintentionally revealing users' private attributes (e.g., gender or race). This risk becomes particularly concerning when the training data contains user…

Past research has demonstrated that the explicit use of protected attributes in machine learning can improve both performance and fairness. Many machine learning algorithms, however, cannot directly process categorical attributes, such as…

Attribute-controlled text rewriting, also known as text style-transfer, has a crucial role in regulating attributes and biases of textual training data and a machine generated text. In this work we present SimpleStyle, a minimalist yet…

This paper addresses the often overlooked issue of fairness in the autonomous driving domain, particularly in vision-based perception and prediction systems, which play a pivotal role in the overall functioning of Autonomous Vehicles (AVs).…

As algorithmic decision-making systems become more prevalent in society, ensuring the fairness of these systems is becoming increasingly important. Whilst there has been substantial research in building fair algorithmic decision-making…

Recent studies show that auto-encoder based approaches successfully perform language generation, smooth sentence interpolation, and style transfer over unseen attributes using unlabelled datasets in a zero-shot manner. The latent space…

Explainable Artificial Intelligence (XAI) aims to make machine learning models transparent and trustworthy, yet most current approaches communicate explanations visually or through text. This paper introduces an information theoretic…

Data cleaning is often framed as a technical preprocessing step, yet in practice it relies heavily on human judgment. We report results from a controlled survey study in which participants performed error detection, data repair and…

The meteoric rise in text generation capability has been accompanied by parallel growth in interest in machine-generated text detection: the capability to identify whether a given text was generated using a model or written by a person.…

Language models are prone to dataset biases, known as shortcuts and spurious correlations in data, which often result in performance drop on new data. We present a new debiasing framework called ``FairFlow'' that mitigates dataset biases by…

Plagiarism in programming assignments is a persistent issue in computer science education, increasingly complicated by the emergence of automated obfuscation attacks. While software plagiarism detectors are widely used to identify…

In this pioneering study, we introduce StyleWallfacer, a groundbreaking unified training and inference framework, which not only addresses various issues encountered in the style transfer process of traditional methods but also unifies the…

In widely used neural network-based collaborative filtering models, users' history logs are encoded into latent embeddings that represent the users' preferences. In this setting, the models are capable of mapping users' protected attributes…

The increasing prevalence of AI-generated content alongside human-written text underscores the need for reliable discrimination methods. To address this challenge, we propose a novel framework with textual embeddings from Pre-trained…

This thesis advances the computational understanding and manipulation of text styles through three interconnected pillars: (1) Text Style Transfer (TST), which alters stylistic properties (e.g., sentiment, formality) while preserving…

Style analysis, which is relatively a less explored topic, enables several interesting applications. For instance, it allows authors to adjust their writing style to produce a more coherent document in collaboration. Similarly, style…

Recent works find that AI algorithms learn biases from data. Therefore, it is urgent and vital to identify biases in AI algorithms. However, the previous bias identification pipeline overly relies on human experts to conjecture potential…

Speech embeddings often retain sensitive attributes such as speaker identity, accent, or demographic information, posing risks in biased model training and privacy leakage. We propose WavShape, an information-theoretic speech representation…